HS project

Zoom in IFE granular and spinous

This file is used to analyse the IFE granular and spinous dataset.

library(dplyr)
library(patchwork)
library(ggplot2)
library(ComplexHeatmap)

.libPaths()

## [1] "/home/nf1/R/x86_64-pc-linux-gnu-library/3.6"
## [2] "/usr/local/lib/R/library"

Preparation

In this section, we set the global settings of the analysis. We will store data there :

save_name = "ifegs"
out_dir = "."

We load the dataset :

sobj = readRDS(paste0(out_dir, "/", save_name, "_sobj.rds"))
sobj

## An object of class Seurat 
## 14702 features across 858 samples within 1 assay 
## Active assay: RNA (14702 features, 2000 variable features)
##  6 dimensional reductions calculated: RNA_pca, RNA_pca_23_tsne, RNA_pca_23_umap, harmony, harmony_23_umap, harmony_23_tsne

We load the sample information :

sample_info = readRDS(paste0(out_dir, "/../../1_metadata/hs_hd_sample_info.rds"))
project_names_oi = sample_info$project_name

graphics::pie(rep(1, nrow(sample_info)),
              col = sample_info$color,
              labels = sample_info$project_name)

Here are custom colors for each cell type :

color_markers = readRDS(paste0(out_dir, "/../../1_metadata/hs_hd_color_markers.rds"))

data.frame(cell_type = names(color_markers),
           color = unlist(color_markers)) %>%
  ggplot2::ggplot(., aes(x = cell_type, y = 0, fill = cell_type)) +
  ggplot2::geom_point(pch = 21, size = 5) +
  ggplot2::scale_fill_manual(values = unlist(color_markers), breaks = names(color_markers)) +
  ggplot2::theme_classic() +
  ggplot2::theme(legend.position = "none",
                 axis.line = element_blank(),
                 axis.title = element_blank(),
                 axis.ticks = element_blank(),
                 axis.text.y = element_blank(),
                 axis.text.x = element_text(angle = 30, hjust = 1))

This is the projection of interest :

name2D = "harmony_23_tsne"

We design a custom function to make the GSEA plot and a word cloud graph :

make_gsea_plot = function(gsea_results, gs_oi, fold_change, metric = "FC") {
  fold_change$metric = fold_change[, metric]
  
  plot_list = lapply(gs_oi, FUN = function(gene_set) {
    # Gene set content
    gs_content = gene_sets %>%
      dplyr::filter(gs_name == gene_set) %>%
      dplyr::pull(ensembl_gene) %>%
      unique()
    
    # Gene set size
    nb_genes = length(gs_content)
    
    # Enrichment metrics
    NES = gsea_results@result[gene_set, "NES"]
    p.adjust = gsea_results@result[gene_set, "p.adjust"] %>%
      round(., 4)
    qvalues = gsea_results@result[gene_set, "qvalues"]
    
    if (p.adjust > 0.05) {
      p.adjust = paste0("<span style='color:red;'>", p.adjust, "</span>")
    }
    
    my_subtitle = paste0("\nNES : ", round(NES, 2),
                         " | padj : ", p.adjust,
                         " | qval : ", round(qvalues, 4),
                         " | set size : ", nb_genes, " genes")
    
    # Size limits
    lower_FC = min(fold_change[gs_content, ]$metric, na.rm = TRUE)
    upper_FC = max(fold_change[gs_content, ]$metric, na.rm = TRUE)
    
    # Plot
    p = enrichplot::gseaplot2(x = gsea_results, geneSetID = gene_set) +
      ggplot2::labs(title = gene_set,
                    subtitle = my_subtitle) +
      ggplot2::theme(plot.title = element_text(hjust = 0.5, face = "bold",
                                               margin = ggplot2::margin(3, 3, 5, 3)),
                     plot.subtitle = ggtext::element_markdown(hjust = 0.5,
                                                              size = 10))
    
    wc = ggplot2::ggplot(fold_change[gs_content, ],
                         aes(label = gene_name, size = abs(metric), color = metric)) +
      ggwordcloud::geom_text_wordcloud_area(show.legend = TRUE) +
      ggplot2::scale_color_gradient2(
        name = metric,
        low = aquarius::color_cnv[1],
        mid = "gray70", midpoint = 0,
        high = aquarius::color_cnv[3]) +
      ggplot2::scale_size_area(max_size = 7) +
      ggplot2::theme_minimal() +
      ggplot2::guides(size = "none")
    
    return(list(p, wc))
  }) %>% unlist(., recursive = FALSE)
  
  return(plot_list)
}

Visualization

Gene expression

We visualize gene expression for some markers :

features = c("percent.mt", "nFeature_RNA", "TOP2A",
             "SPINK5", "KRT1", "KRTDAP")

plot_list = lapply(features, FUN = function(one_gene) {
  Seurat::FeaturePlot(sobj, features = one_gene,
                      reduction = name2D) +
    ggplot2::theme(aspect.ratio = 1) +
    ggplot2::scale_color_gradientn(colors = aquarius::color_gene) +
    Seurat::NoAxes()
})

patchwork::wrap_plots(plot_list, ncol = 3)

Clusters

We visualize clusters :

cluster_plot = Seurat::DimPlot(sobj, reduction = name2D, label = TRUE) +
  Seurat::NoAxes() +
  ggplot2::theme(aspect.ratio = 1)
cluster_plot

Cluster annotation

KRT1 and KRTDAP being specifically expressed in IFE spinous, we make a cluster annotation:

sobj$cluster_type = ifelse(sobj$seurat_clusters %in% c(0,7,5),
                           yes = "IFE spinous",
                           no = "IFE granular")
sobj$cluster_type = ifelse(sobj$seurat_clusters == 10,
                           yes = "IFE proliferative",
                           no = sobj$cluster_type)
cluster_color = setNames(nm = c("IFE spinous", "IFE granular", "IFE proliferative"),
                         c("steelblue4", "lightskyblue", "gray50"))

We visualize the cluster annotation split by sample :

plot_list = aquarius::plot_split_dimred(sobj,
                                        reduction = name2D,
                                        split_by = "project_name",
                                        group_by = "cluster_type",
                                        split_color = setNames(sample_info$color,
                                                               nm = sample_info$project_name),
                                        group_color = cluster_color,
                                        bg_pt_size = 0.5, main_pt_size = 0.5)

plot_list[[length(plot_list) + 1]] = Seurat::DimPlot(sobj, reduction = name2D,
                                                     group.by = "cluster_type") +
  ggplot2::scale_color_manual(values = cluster_color,
                              breaks = names(cluster_color)) +
  Seurat::NoAxes() +
  ggplot2::theme(aspect.ratio = 1)

patchwork::wrap_plots(plot_list, ncol = 4) &
  Seurat::NoLegend()

Differential expression

We save the results in a list :

list_results = list()

We make over-representation analysis for each group of genes. We load gene sets from MSigDB :

gene_sets = aquarius::get_gene_sets(species = "Homo sapiens")
gene_sets = gene_sets$gene_sets

head(gene_sets)

## # A tibble: 6 × 16
##   gs_cat gs_subcat gs_name gene_symbol entrez_gene ensembl_gene human_gene_symb…
##   <chr>  <chr>     <chr>   <chr>             <int> <chr>        <chr>           
## 1 C5     GO:BP     GOBP_1… AASDHPPT          60496 ENSG0000014… AASDHPPT        
## 2 C5     GO:BP     GOBP_1… ALDH1L1           10840 ENSG0000014… ALDH1L1         
## 3 C5     GO:BP     GOBP_1… ALDH1L2          160428 ENSG0000013… ALDH1L2         
## 4 C5     GO:BP     GOBP_1… MTHFD1             4522 ENSG0000010… MTHFD1          
## 5 C5     GO:BP     GOBP_1… MTHFD1L           25902 ENSG0000012… MTHFD1L         
## 6 C5     GO:BP     GOBP_1… MTHFD2L          441024 ENSG0000016… MTHFD2L         
## # … with 9 more variables: human_entrez_gene <int>, human_ensembl_gene <chr>,
## #   gs_id <chr>, gs_pmid <chr>, gs_geoid <chr>, gs_exact_source <chr>,
## #   gs_url <chr>, gs_description <chr>, category <chr>

How many gene sets ?

gene_sets[, c("gs_subcat", "gs_name")] %>%
  dplyr::distinct() %>%
  dplyr::pull(gs_subcat) %>%
  table() %>%
  as.data.frame.table() %>%
  `colnames<-`(c("Category", "Nb gene sets"))

##          Category Nb gene sets
## 1                           50
## 2         CP:KEGG          186
## 3          CP:PID          196
## 4     CP:REACTOME         1615
## 5 CP:WIKIPATHWAYS          664
## 6           GO:BP         7658
## 7           GO:CC         1006
## 8           GO:MF         1738

We get gene name and gene ID correspondence :

gene_corresp = sobj@assays[["RNA"]]@meta.features[, c("gene_name", "Ensembl_ID")] %>%
  `colnames<-`(c("NAME", "ID")) %>%
  dplyr::mutate(ID = as.character(ID))
rownames(gene_corresp) = gene_corresp$ID

head(gene_corresp)

##                       NAME              ID
## ENSG00000238009 AL627309.1 ENSG00000238009
## ENSG00000237491 AL669831.5 ENSG00000237491
## ENSG00000225880  LINC00115 ENSG00000225880
## ENSG00000230368     FAM41C ENSG00000230368
## ENSG00000230699 AL645608.3 ENSG00000230699
## ENSG00000187634     SAMD11 ENSG00000187634

Granular vs spinous

We perform a differential expression analysis between granular and spinous clusters.

group_name = "granular_vs_spinous"

Seurat::Idents(sobj) = sobj$cluster_type
table(Seurat::Idents(sobj))

## 
##      IFE granular       IFE spinous IFE proliferative 
##               569               271                18

DE

We identify DE genes between IFE granular and IFE spinous :

mark = Seurat::FindMarkers(sobj, ident.1 = "IFE granular", ident.2 = "IFE spinous")

mark = mark %>%
  dplyr::filter(p_val_adj < 0.05) %>%
  dplyr::arrange(-avg_logFC, pct.1 - pct.2)

list_results[[group_name]]$mark = mark

dim(mark)

## [1] 178   5

head(mark, n = 20)

##                 p_val avg_logFC pct.1 pct.2    p_val_adj
## CST6     1.312487e-08 2.7812181 0.232 0.081 1.929619e-04
## KRT17    3.146104e-54 2.3543550 0.888 0.513 4.625402e-50
## KRT6B    4.713061e-16 1.4782965 0.779 0.664 6.929142e-12
## SPRR1B   3.393337e-06 1.3897725 0.211 0.092 4.988884e-02
## PTN      2.499803e-38 1.1947052 0.698 0.310 3.675210e-34
## LGALS1   6.326597e-09 0.9863320 0.492 0.343 9.301364e-05
## S100A6   2.753732e-25 0.9788135 0.903 0.867 4.048537e-21
## APOE     7.514251e-45 0.9398667 0.935 0.819 1.104745e-40
## CALML3   1.374189e-31 0.9218625 0.926 0.749 2.020333e-27
## C1QTNF12 3.298999e-41 0.8318747 0.624 0.159 4.850188e-37
## CCL2     3.221356e-08 0.7510733 0.169 0.037 4.736038e-04
## CHI3L1   1.904183e-36 0.7379103 0.496 0.044 2.799530e-32
## S100A7   2.692190e-12 0.6861332 0.814 0.616 3.958058e-08
## S100A2   2.641968e-14 0.6805155 0.954 0.963 3.884221e-10
## CSTB     1.833595e-26 0.6404838 0.963 0.956 2.695751e-22
## CYP1B1   9.017717e-27 0.5955697 0.390 0.037 1.325785e-22
## DAPK2    1.466078e-27 0.5945600 0.573 0.255 2.155429e-23
## C9orf16  1.898308e-17 0.5918988 0.859 0.882 2.790893e-13
## CREG1    5.690539e-17 0.5881386 0.750 0.661 8.366230e-13
## CKB      4.937212e-11 0.5766541 0.640 0.513 7.258688e-07

Up in IFE granular

We explore enrichment in gene sets for HS population.

genes_of_interest = mark %>%
  dplyr::filter(avg_logFC > 0) %>%
  rownames()

enrichr_results = aquarius::run_enrichr(gene_names = genes_of_interest,
                                        gene_corresp = gene_corresp,
                                        gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                        make_plot = TRUE,
                                        plot_title = "Up-regulated in IFE granular compared to IFE spinous")

list_results[[group_name]]$enrichr_hs = enrichr_results$ego

enrichr_results$plot +
  ggplot2::theme(axis.text.y = element_text(size = 8))

Up in IFE spinous

We explore enrichment in gene sets for HD population.

genes_of_interest = mark %>%
  dplyr::filter(avg_logFC < 0) %>%
  rownames()

enrichr_results = aquarius::run_enrichr(gene_names = genes_of_interest,
                                        gene_corresp = gene_corresp,
                                        gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                        make_plot = TRUE,
                                        plot_title = "Down-regulated in IFE granular compared to IFE spinous")

list_results[[group_name]]$enrichr_hd = enrichr_results$ego

enrichr_results$plot +
  ggplot2::theme(axis.text.y = element_text(size = 8))

GSEA

We run a GSEA for all gene sets, from the full count matrix :

ranked_gene_list = aquarius::run_foldchange(Seurat::GetAssayData(sobj, assay = "RNA", slot = "counts"),
                                            group1 = colnames(sobj)[sobj@active.ident %in% "IFE granular"],
                                            group2 = colnames(sobj)[sobj@active.ident %in% "IFE spinous"])
names(ranked_gene_list) = gene_corresp$ID

gsea_results = aquarius::gsea_run(ranked_gene_list = ranked_gene_list,
                                  gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                  GSEA_p_val_thresh = 1)

list_results[[group_name]]$gsea = gsea_results

gsea_results@result %>%
  dplyr::filter(pvalue < 0.05) %>%
  dplyr::top_n(., n = 200, wt = abs(NES)) %>%
  dplyr::mutate(too_long = ifelse(nchar(ID) > 60, yes = TRUE, no = FALSE)) %>%
  dplyr::mutate(ID = stringr::str_sub(ID, end = 60)) %>%
  dplyr::mutate(ID = ifelse(too_long, yes = paste0(ID, "..."), no = ID)) %>%
  aquarius::gsea_plot(show_legend = TRUE) +
  ggplot2::labs(title = "GSEA using all genes (count matrix)") +
  ggplot2::theme(plot.title = element_text(size = 20))

We compute a fold change table to make a wordcloud :

fold_change = gene_corresp
colnames(fold_change) = c("gene_name", "ID")
rownames(fold_change) = fold_change$ID
fold_change$FC = ranked_gene_list[rownames(fold_change)]
fold_change$pct.1 = Seurat::GetAssayData(sobj, assay = "RNA",
                                         slot = "counts")[, sobj@active.ident == "IFE granular"] %>%
  apply(., MARGIN = 1, FUN = function(one_row) {
    return( mean(one_row != 0) )
  })
fold_change$pct.2 = Seurat::GetAssayData(sobj, assay = "RNA",
                                         slot = "counts")[, sobj@active.ident == "IFE spinous"] %>%
  apply(., MARGIN = 1, FUN = function(one_row) {
    return( mean(one_row != 0) )
  })
fold_change$FC_x_pct = ifelse(fold_change$FC > 0,
                              yes = fold_change$FC * fold_change$pct.1,
                              no = fold_change$FC * fold_change$pct.2)

dim(fold_change) ; head(fold_change)

## [1] 14702     6

##                  gene_name              ID         FC       pct.1      pct.2
## ENSG00000238009 AL627309.1 ENSG00000238009 -1.6543733 0.003514938 0.01845018
## ENSG00000237491 AL669831.5 ENSG00000237491 -0.5753017 0.105448155 0.21771218
## ENSG00000225880  LINC00115 ENSG00000225880 -1.1568736 0.038664323 0.11439114
## ENSG00000230368     FAM41C ENSG00000230368  0.3025580 0.049209139 0.05904059
## ENSG00000230699 AL645608.3 ENSG00000230699 -0.1398001 0.015817223 0.02214022
## ENSG00000187634     SAMD11 ENSG00000187634 -1.2393358 0.005272408 0.01845018
##                     FC_x_pct
## ENSG00000238009 -0.030523492
## ENSG00000237491 -0.125250187
## ENSG00000225880 -0.132336097
## ENSG00000230368  0.014888619
## ENSG00000230699 -0.003095205
## ENSG00000187634 -0.022865974

We make the gsea plot for some gene sets :

gs_oi = c("GOBP_KERATINIZATION",
          "GOCC_CORNIFIED_ENVELOPE",
          "GOBP_CELLULAR_RESPONSE_TO_COPPER_ION",
          "GOBP_CELLULAR_RESPONSE_TO_CADMIUM_ION",
          "REACTOME_RESPONSE_TO_METAL_IONS",
          "WP_TGFBETA_RECEPTOR_SIGNALING")

plot_list = make_gsea_plot(gsea_results, gs_oi, fold_change, "FC_x_pct")

patchwork::wrap_plots(plot_list, ncol = 2, widths = c(2,1.5))

HS vs HD

We perform a differential expression analysis for all clusters, between HS patients (HS) and healthy donors (HD).

group_name = "HS_vs_HD"

Seurat::Idents(sobj) = sobj$sample_type
table(Seurat::Idents(sobj))

## 
##  HS  HD 
## 745 113

DE

We identify DE genes between HS and HD :

mark = Seurat::FindMarkers(sobj, ident.1 = "HS", ident.2 = "HD")

mark = mark %>%
  dplyr::filter(p_val_adj < 0.05) %>%
  dplyr::arrange(-avg_logFC, pct.1 - pct.2)

list_results[[group_name]]$mark = mark

dim(mark)

## [1] 121   5

head(mark, n = 20)

##                  p_val avg_logFC pct.1 pct.2    p_val_adj
## LGALS7    1.570129e-18 1.5442230 0.626 0.248 2.308404e-14
## LGALS7B   1.397267e-18 1.4997898 0.890 0.796 2.054262e-14
## S100A7    5.847206e-22 1.4868877 0.819 0.336 8.596562e-18
## SERPINB4  8.588334e-09 1.2839572 0.289 0.035 1.262657e-04
## KRT16     3.200379e-09 1.1955128 0.560 0.230 4.705198e-05
## S100A9    1.536359e-17 1.1582099 0.879 0.549 2.258755e-13
## MIF       2.340242e-24 0.9700148 0.701 0.257 3.440623e-20
## FABP5     2.056235e-13 0.8558368 0.934 0.770 3.023076e-09
## SERPINB3  1.213844e-07 0.8363353 0.240 0.018 1.784594e-03
## AKR1B10   9.665634e-23 0.8159507 0.565 0.044 1.421041e-18
## RPS26     4.661145e-39 0.8095101 0.981 0.991 6.852815e-35
## MTRNR2L8  3.707886e-13 0.8073258 0.824 0.743 5.451334e-09
## S100A8    4.880448e-12 0.6928935 0.882 0.628 7.175235e-08
## CRABP2    1.178746e-08 0.5791768 0.713 0.460 1.732992e-04
## HSPA8     2.910521e-14 0.5533035 0.874 0.708 4.279048e-10
## MTRNR2L10 2.541018e-08 0.5521470 0.634 0.478 3.735805e-04
## ARF5      1.167134e-19 0.5149905 0.536 0.071 1.715921e-15
## XIST      2.830229e-09 0.4645008 0.612 0.292 4.161003e-05
## S100A2    1.054239e-08 0.4620684 0.964 0.920 1.549942e-04
## S100A10   7.344198e-11 0.4504742 0.948 0.867 1.079744e-06

Up in HS

We explore enrichment in gene sets for HS population.

genes_of_interest = mark %>%
  dplyr::filter(avg_logFC > 0) %>%
  rownames()

enrichr_results = aquarius::run_enrichr(gene_names = genes_of_interest,
                                        gene_corresp = gene_corresp,
                                        gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                        make_plot = TRUE,
                                        plot_title = "Up-regulated in HS compared to HD")

list_results[[group_name]]$enrichr_hs = enrichr_results$ego

enrichr_results$plot +
  ggplot2::theme(axis.text.y = element_text(size = 8))

Up in HD

We explore enrichment in gene sets for HD population.

genes_of_interest = mark %>%
  dplyr::filter(avg_logFC < 0) %>%
  rownames()

enrichr_results = aquarius::run_enrichr(gene_names = genes_of_interest,
                                        gene_corresp = gene_corresp,
                                        gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                        make_plot = TRUE,
                                        plot_title = "Down-regulated in HS compared to HD")

list_results[[group_name]]$enrichr_hd = enrichr_results$ego

enrichr_results$plot +
  ggplot2::theme(axis.text.y = element_text(size = 8))

GSEA

We run a GSEA for all gene sets, from the full count matrix :

ranked_gene_list = aquarius::run_foldchange(Seurat::GetAssayData(sobj, assay = "RNA", slot = "counts"),
                                            group1 = colnames(sobj)[sobj@active.ident %in% "HS"],
                                            group2 = colnames(sobj)[sobj@active.ident %in% "HD"])
names(ranked_gene_list) = gene_corresp$ID

gsea_results = aquarius::gsea_run(ranked_gene_list = ranked_gene_list,
                                  gene_sets = gene_sets[, c("gs_name", "ensembl_gene")],
                                  GSEA_p_val_thresh = 1)

list_results[[group_name]]$gsea = gsea_results

gsea_results@result %>%
  dplyr::filter(pvalue < 0.05) %>%
  dplyr::top_n(., n = 200, wt = abs(NES)) %>%
  dplyr::mutate(too_long = ifelse(nchar(ID) > 60, yes = TRUE, no = FALSE)) %>%
  dplyr::mutate(ID = stringr::str_sub(ID, end = 60)) %>%
  dplyr::mutate(ID = ifelse(too_long, yes = paste0(ID, "..."), no = ID)) %>%
  aquarius::gsea_plot(show_legend = TRUE) +
  ggplot2::labs(title = "GSEA using all genes (count matrix)") +
  ggplot2::theme(plot.title = element_text(size = 20))

We compute a fold change table to make a wordcloud :

fold_change = gene_corresp
colnames(fold_change) = c("gene_name", "ID")
rownames(fold_change) = fold_change$ID
fold_change$FC = ranked_gene_list[rownames(fold_change)]
fold_change$pct.1 = Seurat::GetAssayData(sobj, assay = "RNA", slot = "counts")[, sobj@active.ident == "HS"] %>%
  apply(., MARGIN = 1, FUN = function(one_row) {
    return( mean(one_row != 0) )
  })
fold_change$pct.2 = Seurat::GetAssayData(sobj, assay = "RNA", slot = "counts")[, sobj@active.ident == "HD"] %>%
  apply(., MARGIN = 1, FUN = function(one_row) {
    return( mean(one_row != 0) )
  })
fold_change$FC_x_pct = ifelse(fold_change$FC > 0,
                              yes = fold_change$FC * fold_change$pct.1,
                              no = fold_change$FC * fold_change$pct.2)

dim(fold_change) ; head(fold_change)

## [1] 14702     6

##                  gene_name              ID          FC       pct.1       pct.2
## ENSG00000238009 AL627309.1 ENSG00000238009 -0.31174748 0.010738255 0.000000000
## ENSG00000237491 AL669831.5 ENSG00000237491  0.06264803 0.153020134 0.079646018
## ENSG00000225880  LINC00115 ENSG00000225880  0.42521811 0.072483221 0.026548673
## ENSG00000230368     FAM41C ENSG00000230368  1.21876723 0.061744966 0.008849558
## ENSG00000230699 AL645608.3 ENSG00000230699 -0.57478189 0.018791946 0.008849558
## ENSG00000187634     SAMD11 ENSG00000187634 -3.67431756 0.005369128 0.035398230
##                     FC_x_pct
## ENSG00000238009  0.000000000
## ENSG00000237491  0.009586410
## ENSG00000225880  0.030821179
## ENSG00000230368  0.075252742
## ENSG00000230699 -0.005086565
## ENSG00000187634 -0.130064338

We make the gsea plot for some gene sets :

gs_oi = c("HALLMARK_INTERFERON_ALPHA_RESPONSE",
          "HALLMARK_INTERFERON_GAMMA_RESPONSE",
          "REACTOME_KERATINIZATION",
          "GOBP_KERATINIZATION",
          "GOBP_MACROPHAGE_CYTOKINE_PRODUCTION",
          "GOCC_MHC_PROTEIN_COMPLEX",
          "KEGG_ANTIGEN_PROCESSING_AND_PRESENTATION")

plot_list = make_gsea_plot(gsea_results, gs_oi, fold_change, "FC_x_pct")

patchwork::wrap_plots(plot_list, ncol = 2, widths = c(2,1.5))

Visualisation

We represent differentially expressed genes. First, we extract all DE genes :

features_oi = list_results[[group_name]]$mark %>%
  dplyr::filter(p_val_adj < 0.05) %>%
  dplyr::filter(pct.1 - pct.2 > 0.2 | abs(avg_logFC) > 1) %>%
  rownames()

length(features_oi)

## [1] 29

We prepare the scaled expression matrix :

mat_expression = Seurat::GetAssayData(sobj, assay = "RNA", slot = "data")[features_oi, ]
mat_expression = Matrix::t(mat_expression)
mat_expression = dynutils::scale_quantile(mat_expression) # between 0 and 1
mat_expression = Matrix::t(mat_expression)
mat_expression = as.matrix(mat_expression) # not sparse

dim(mat_expression)

## [1]  29 858

We prepare the heatmap annotation :

ha_top = ComplexHeatmap::HeatmapAnnotation(
  sample_type = sobj$sample_type,
  cluster_type = sobj$cluster_type,
  cluster = sobj$seurat_clusters,
  col = list(sample_type = setNames(nm = c("HS", "HD"),
                                    c("#C55F40", "#2C78E6")),
             cluster_type = cluster_color,
             cluster = setNames(nm = levels(sobj$seurat_clusters),
                                aquarius::gg_color_hue(length(levels(sobj$seurat_clusters))))))

And the heatmap :

ht = ComplexHeatmap::Heatmap(mat_expression,
                             col = aquarius::color_cnv,
                             # Annotation
                             top_annotation = ha_top,
                             # Grouping
                             column_order = sobj@meta.data %>%
                               dplyr::arrange(cluster_type, sample_type, seurat_clusters) %>%
                               rownames(),
                             column_title = NULL,
                             cluster_rows = FALSE,
                             cluster_columns = FALSE,
                             show_column_names = FALSE,
                             # Visual aspect
                             show_heatmap_legend = TRUE,
                             border = TRUE)

ComplexHeatmap::draw(ht,
                     merge_legend = TRUE,
                     heatmap_legend_side = "bottom",
                     annotation_legend_side = "bottom")

Save

We save the list of results :

saveRDS(list_results, file = paste0(out_dir, "/", save_name, "_list_results.rds"))

R Session

show

## R version 3.6.3 (2020-02-29)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 24.04.1 LTS
## 
## Matrix products: default
## BLAS:   /usr/local/lib/R/lib/libRblas.so
## LAPACK: /usr/local/lib/R/lib/libRlapack.so
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] grid      stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
## [1] ComplexHeatmap_2.14.0 ggplot2_3.3.5         patchwork_1.1.2      
## [4] dplyr_1.0.7          
## 
## loaded via a namespace (and not attached):
##   [1] softImpute_1.4              graphlayouts_0.7.0         
##   [3] pbapply_1.4-2               lattice_0.20-41            
##   [5] haven_2.3.1                 vctrs_0.3.8                
##   [7] usethis_2.0.1               dynwrap_1.2.1              
##   [9] blob_1.2.1                  survival_3.2-13            
##  [11] prodlim_2019.11.13          dynutils_1.0.5             
##  [13] later_1.3.0                 DBI_1.1.1                  
##  [15] R.utils_2.11.0              SingleCellExperiment_1.8.0 
##  [17] rappdirs_0.3.3              uwot_0.1.8                 
##  [19] dqrng_0.2.1                 jpeg_0.1-8.1               
##  [21] zlibbioc_1.32.0             pspline_1.0-18             
##  [23] pcaMethods_1.78.0           mvtnorm_1.1-1              
##  [25] htmlwidgets_1.5.4           GlobalOptions_0.1.2        
##  [27] future_1.22.1               UpSetR_1.4.0               
##  [29] laeken_0.5.2                leiden_0.3.3               
##  [31] clustree_0.4.3              parallel_3.6.3             
##  [33] scater_1.14.6               irlba_2.3.3                
##  [35] markdown_1.1                DEoptimR_1.0-9             
##  [37] tidygraph_1.1.2             Rcpp_1.0.9                 
##  [39] readr_2.0.2                 KernSmooth_2.23-17         
##  [41] carrier_0.1.0               promises_1.1.0             
##  [43] gdata_2.18.0                DelayedArray_0.12.3        
##  [45] limma_3.42.2                graph_1.64.0               
##  [47] RcppParallel_5.1.9          Hmisc_4.4-0                
##  [49] fs_1.5.2                    RSpectra_0.16-0            
##  [51] fastmatch_1.1-0             ranger_0.12.1              
##  [53] digest_0.6.25               png_0.1-7                  
##  [55] sctransform_0.2.1           cowplot_1.0.0              
##  [57] DOSE_3.12.0                 here_1.0.1                 
##  [59] TInGa_0.0.0.9000            ggraph_2.0.3               
##  [61] pkgconfig_2.0.3             GO.db_3.10.0               
##  [63] DelayedMatrixStats_1.8.0    gower_0.2.1                
##  [65] ggbeeswarm_0.6.0            iterators_1.0.12           
##  [67] DropletUtils_1.6.1          reticulate_1.26            
##  [69] clusterProfiler_3.14.3      SummarizedExperiment_1.16.1
##  [71] circlize_0.4.15             beeswarm_0.4.0             
##  [73] GetoptLong_1.0.5            xfun_0.35                  
##  [75] bslib_0.3.1                 zoo_1.8-10                 
##  [77] tidyselect_1.1.0            reshape2_1.4.4             
##  [79] purrr_0.3.4                 ica_1.0-2                  
##  [81] pcaPP_1.9-73                viridisLite_0.3.0          
##  [83] rtracklayer_1.46.0          rlang_1.0.2                
##  [85] hexbin_1.28.1               jquerylib_0.1.4            
##  [87] dyneval_0.9.9               glue_1.4.2                 
##  [89] RColorBrewer_1.1-2          matrixStats_0.56.0         
##  [91] stringr_1.4.0               lava_1.6.7                 
##  [93] europepmc_0.3               DESeq2_1.26.0              
##  [95] recipes_0.1.17              labeling_0.3               
##  [97] httpuv_1.5.2                class_7.3-17               
##  [99] BiocNeighbors_1.4.2         DO.db_2.9                  
## [101] annotate_1.64.0             jsonlite_1.7.2             
## [103] XVector_0.26.0              bit_4.0.4                  
## [105] mime_0.9                    aquarius_0.1.5             
## [107] Rsamtools_2.2.3             gridExtra_2.3              
## [109] gplots_3.0.3                stringi_1.4.6              
## [111] processx_3.5.2              gsl_2.1-6                  
## [113] bitops_1.0-6                cli_3.0.1                  
## [115] batchelor_1.2.4             RSQLite_2.2.0              
## [117] randomForest_4.6-14         tidyr_1.1.4                
## [119] data.table_1.14.2           rstudioapi_0.13            
## [121] org.Mm.eg.db_3.10.0         GenomicAlignments_1.22.1   
## [123] nlme_3.1-147                qvalue_2.18.0              
## [125] scran_1.14.6                locfit_1.5-9.4             
## [127] scDblFinder_1.1.8           listenv_0.8.0              
## [129] ggthemes_4.2.4              gridGraphics_0.5-0         
## [131] R.oo_1.24.0                 dbplyr_1.4.4               
## [133] BiocGenerics_0.32.0         TTR_0.24.2                 
## [135] readxl_1.3.1                lifecycle_1.0.1            
## [137] timeDate_3043.102           ggpattern_0.3.1            
## [139] munsell_0.5.0               cellranger_1.1.0           
## [141] R.methodsS3_1.8.1           proxyC_0.1.5               
## [143] visNetwork_2.0.9            caTools_1.18.0             
## [145] codetools_0.2-16            ggwordcloud_0.5.0          
## [147] Biobase_2.46.0              GenomeInfoDb_1.22.1        
## [149] vipor_0.4.5                 lmtest_0.9-38              
## [151] msigdbr_7.5.1               htmlTable_1.13.3           
## [153] triebeard_0.3.0             lsei_1.3-0                 
## [155] xtable_1.8-4                ROCR_1.0-7                 
## [157] BiocManager_1.30.10         scatterplot3d_0.3-41       
## [159] abind_1.4-5                 farver_2.0.3               
## [161] parallelly_1.28.1           RANN_2.6.1                 
## [163] askpass_1.1                 GenomicRanges_1.38.0       
## [165] RcppAnnoy_0.0.16            tibble_3.1.5               
## [167] ggdendro_0.1-20             cluster_2.1.0              
## [169] future.apply_1.5.0          Seurat_3.1.5               
## [171] dendextend_1.15.1           Matrix_1.3-2               
## [173] ellipsis_0.3.2              prettyunits_1.1.1          
## [175] lubridate_1.7.9             ggridges_0.5.2             
## [177] igraph_1.2.5                RcppEigen_0.3.3.7.0        
## [179] fgsea_1.12.0                remotes_2.4.2              
## [181] scBFA_1.0.0                 destiny_3.0.1              
## [183] VIM_6.1.1                   testthat_3.1.0             
## [185] htmltools_0.5.2             BiocFileCache_1.10.2       
## [187] yaml_2.2.1                  utf8_1.1.4                 
## [189] plotly_4.9.2.1              XML_3.99-0.3               
## [191] ModelMetrics_1.2.2.2        e1071_1.7-3                
## [193] foreign_0.8-76              withr_2.5.0                
## [195] fitdistrplus_1.0-14         BiocParallel_1.20.1        
## [197] xgboost_1.4.1.1             bit64_4.0.5                
## [199] foreach_1.5.0               robustbase_0.93-9          
## [201] Biostrings_2.54.0           GOSemSim_2.13.1            
## [203] rsvd_1.0.3                  memoise_2.0.0              
## [205] evaluate_0.18               forcats_0.5.0              
## [207] rio_0.5.16                  geneplotter_1.64.0         
## [209] tzdb_0.1.2                  caret_6.0-86               
## [211] ps_1.6.0                    DiagrammeR_1.0.6.1         
## [213] curl_4.3                    fdrtool_1.2.15             
## [215] fansi_0.4.1                 highr_0.8                  
## [217] urltools_1.7.3              xts_0.12.1                 
## [219] GSEABase_1.48.0             acepack_1.4.1              
## [221] edgeR_3.28.1                checkmate_2.0.0            
## [223] scds_1.2.0                  cachem_1.0.6               
## [225] npsurv_0.4-0                babelgene_22.3             
## [227] rjson_0.2.20                openxlsx_4.1.5             
## [229] ggrepel_0.9.1               clue_0.3-60                
## [231] rprojroot_2.0.2             stabledist_0.7-1           
## [233] tools_3.6.3                 sass_0.4.0                 
## [235] nichenetr_1.1.1             magrittr_2.0.1             
## [237] RCurl_1.98-1.2              proxy_0.4-24               
## [239] car_3.0-11                  ape_5.3                    
## [241] ggplotify_0.0.5             xml2_1.3.2                 
## [243] httr_1.4.2                  assertthat_0.2.1           
## [245] rmarkdown_2.18              boot_1.3-25                
## [247] globals_0.14.0              R6_2.4.1                   
## [249] Rhdf5lib_1.8.0              nnet_7.3-14                
## [251] RcppHNSW_0.2.0              progress_1.2.2             
## [253] genefilter_1.68.0           statmod_1.4.34             
## [255] gtools_3.8.2                shape_1.4.6                
## [257] HDF5Array_1.14.4            BiocSingular_1.2.2         
## [259] rhdf5_2.30.1                splines_3.6.3              
## [261] AUCell_1.8.0                carData_3.0-4              
## [263] colorspace_1.4-1            generics_0.1.0             
## [265] stats4_3.6.3                base64enc_0.1-3            
## [267] dynfeature_1.0.0            smoother_1.1               
## [269] gridtext_0.1.1              pillar_1.6.3               
## [271] tweenr_1.0.1                sp_1.4-1                   
## [273] ggplot.multistats_1.0.0     rvcheck_0.1.8              
## [275] GenomeInfoDbData_1.2.2      plyr_1.8.6                 
## [277] gtable_0.3.0                zip_2.2.0                  
## [279] knitr_1.41                  latticeExtra_0.6-29        
## [281] biomaRt_2.42.1              IRanges_2.20.2             
## [283] fastmap_1.1.0               ADGofTest_0.3              
## [285] copula_1.0-0                doParallel_1.0.15          
## [287] AnnotationDbi_1.48.0        vcd_1.4-8                  
## [289] babelwhale_1.0.1            openssl_1.4.1              
## [291] scales_1.1.1                backports_1.2.1            
## [293] S4Vectors_0.24.4            ipred_0.9-12               
## [295] enrichplot_1.6.1            hms_1.1.1                  
## [297] ggforce_0.3.1               Rtsne_0.15                 
## [299] shiny_1.7.1                 numDeriv_2016.8-1.1        
## [301] polyclip_1.10-0             lazyeval_0.2.2             
## [303] Formula_1.2-3               tsne_0.1-3                 
## [305] crayon_1.3.4                MASS_7.3-54                
## [307] pROC_1.16.2                 viridis_0.5.1              
## [309] dynparam_1.0.0              rpart_4.1-15               
## [311] zinbwave_1.8.0              compiler_3.6.3             
## [313] ggtext_0.1.0